The Comparison of Machine Learning Models for Predicting of Coffee Berry Borer Infestation

The objective of this study is to compare machine learning models for predicting coffee berry borer infestations in 4 Arabica coffee growing areas from 2 provinces: Pa Miang Royal Project Development Center, Tape Sadet Sub-district, Doi Saked District, Chiang Mai, Teen Tok Royal Project Development Center, Huay Kaew Sub-district, Mae On District, Chiang Mai, Huay Pong Royal Project Development Center, Mae Jae Dee Mai Sub-district, Wieng Pa Pao District, Chiang Rai, and Huay Nam Khun Royal Project Development Center, Ta Kau Sub-district, Mae Sa Rauy District, Chiang Rai. Monthly data, the number of coffee berry borer (amount/1,800 square meters) and climate data in each area, including temperature, maximum temperature and lowest temperature (degrees Celsius), relative humidity (percent), wind speed (meters per second) and rainfall (millimeter per day) were collected for 2 years. Data were divided into 2 parts: training set (80%) for constructing machine learning model, Support Vector Regression (SVR), Artificial Neural Network (ANN) and Random Forest (RF), and test set (20%) for evaluating model performance with root mean square error (RMSE) and coefficient of determination. Furthermore, future monthly climate data in 2025 and 2030 with two climate change scenarios, SSP2-4.5 and SSP5-8.5, were downloaded and employed to predict future coffee berry borer epidemics with the best model.

It had been found that support vector regression is the most effective in predicting the coffee berry borer epidemics (R2=32.36%, RMSE = 42.91). The best model, SVR was applied with future monthly climate data to predict future epidemics. It predicted a severe epidemic in 2025 and 2030. With SSP5-8.5 scenarios, in 2025 Chiang Mai would have the most severe epidemics of coffee berry borer, 21.41 percent, while Chiang Rai had a severe epidemic only 11.41 percent. Therefore, it may be concluded that areas in Chiang Mai would be more prone to coffee berry borer epidemics than areas in Chiang Rai.